Run 4. Outer Step 7. Inner Step 73.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5494811,
-    5494816,
-    5494821,
-    5494826,
-    5494831
+    5494837,
+    5494843,
+    5494848,
+    5494853,
+    5494860
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 72,
+  "inner_step": 73,
   "inner_steps": 0,
   "last_allreduce_block": 5473073,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc1801d624aec3aaee4be5ec75ca5ec8a431eb4c7f88abc4266e2860264c8b52
+oid sha256:99489221cd67cd5664cb2a092f8cb26c088887934d26b262316b3b98e299d7cb
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2100f3bd2444fb85ed7eb97c441ba89d8d22d1406a5913512aa051d5071a1961
+oid sha256:b2c7d7373943d19e7a69cdc9804afb58f72c7a011af3163cec9ff3a52ad133bb
 size 4040701744